Qualitative description & statistics

Question 1

discrete variables

Answer 1

dichotomous = binary (female/male)
categorical = nominal ( bus, bike, walk)
ordinal ( very satisfied –> neutral –> dissatisfied)

Question 2

discrete variables

Answer 2

dichotomous = binary (female/male)
categorical = nominal ( bus, bike, walk)
ordinal ( very satisfied –> neutral –> dissatisfied)

Question 3

interval (i.e. differences are meaningful) = numerical

Answer 3

count
ratio ( height)
continuous (time)

Question 4

measurement

Answer 4

precision vs accuracy
significant figures

Question 5

describing distributions

Answer 5

univariate or bivariate

Question 6

univariate

Answer 6

normal
uniform
bimodal
U-shaped
skewed

Question 7

descriptive stats

Answer 7

measures of central tendency
measures of variation
shape ( higher moments)

Question 8

measures of central tendency

Answer 8

mean, median, mode

Question 9

measures of variation

Answer 9

range, variance and standard deviation, quantiles, percentiles, inter-quartile

Question 10

shape (higher moments)

Answer 10

variance, skewness, kurtosis

Question 11

confidence

Answer 11

standard error
confidence interval ( credible interval)
statistical significance
scientific/ economic/ clinical significance

Question 12

likert scale example

Answer 12

strongly disagree–> disagree–> neutral –> agree –> strongly agree
( this data is categorical, ordinal, dichotomous, continuous)

Question 13

accuracy

Answer 13

true. consistent with the truth or objective (unbiased)

Question 14

precise

Answer 14

detailed, specific, having low uncertainty, highly resolved

Question 15

measurement e.g. the flood water is 35 cm deep, plus or minus half a cm

Answer 15

when we measure something in science, we always provide an estimate of our confidence along with the measurement

Question 16

estimation e.g. ospreys live on average 38.4 +/- 5 years

Answer 16

when we statistically estimate something that was not measured directly, or infer something about the world through our research methods, we must also calculate a measure of confidence for what we report

Question 17

communicating precision = probabilistic statements

Answer 17

between 31% and 37% with 95 % confidence ( i.e., e [31%,37%] 19 times out of 20)

Question 18

displaying univariate qualitative (categorical) data

Answer 18

tables, bar charts, pie charts

Question 19

displaying univariate continuous data

Answer 19

histogram, box plot, kernel density estimation (carpet plot)

Question 20

bivariate plots: two categorical variable

Answer 20

paired bar plots

Question 21

how to visualize –> bivariate plots : one categorical, one continuous variable

Answer 21

multiple histograms, box plots

Question 22

visualize –> bivariate plots: two continuous variables

Answer 22

scatter plots

Question 23

univariate measures of dispersion

Answer 23

range
standard deviation: average distance from the mean, coefficient of variation, index of dispersion, interquartile range

Question 24

measures of shape

Answer 24

variance, skewness, kurtossis, L-moments

Question 25

Skewness Left (negative), Right (positive)

Answer 25

(a) negative direction ( mean - median - mode) (b) positive direction ( mode -median-mean)

Question 26

confidence interval

Answer 26

the range within which we would expect the value of the statistics to fall, if we were to repeat the study with a very large sample

Question 27

what does confidence depend on?

Answer 27

sample spread, sample size, ( the nature of the statistic you're estimating )

Question 28

credible intervals are a simpler concept from bayesian stats

Answer 28

the interval within which an unobserved parameter value falls with a particular probability, given available data, model, and preexisting knowledge - best estimate of the true value of parameter

Question 29

properties of a univariate variable

Answer 29

ex: describe (aspects of) the distribution of an unordered list of sample measurements

Question 30

multivariate properties

Answer 30

-two things measured for each individual sampled - describes (aspects of) the relationship between theme

Question 31

univariate measures of central tendency

Answer 31

mean, median, mode

Question 32

statistical significance

Answer 32

"within 3%, 19 times out of 20" - closely related to confidence intervals = error bars

Question 33

scientific ( or economic) significance

Answer 33

an estimate of effect size put into context, for instance by competing effects, natural variation, or comparison to other costs or impacts